Abstract Liver disease in patients is on the rise due to environmental factors like toxic gas exposure, contaminated food, drug interactions, and excessive alcohol use. Therefore, diagnosing liver disease is crucial for saving lives and managing the condition effectively. In this paper, a new method called Liver Patients Detection Strategy (LPDS) is proposed for diagnosing liver disease in patients from laboratory data alone. The three main parts of LPDS are data preprocessing, feature selection, and detection. The data from the patient is processed, and any anomalies are removed during this stage. Then, during feature selection phase, the most helpful features are chosen. A novel method is proposed to choose the most relevant features during the feature selection stage. The formal name for this method is IB 2 OA, which stands for Improved Binary Butterfly Optimization Algorithm. There are two steps to IB 2 OA, which are; Primary Selection (PS) step and Final Selection (FS) step. This paper presents two enhancements. The first is Information Gain (IG) approach, which is used for initial feature reduction. The second is implementing BOA's initialization with Optimization Based on Opposition (OBO). Finally, five different classifiers, which are Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naive Bayes (NB), Decision Tree (DT), and Random Forest (RF) are used to identify patients with liver disease during the detection phase. Results from a battery of experiments show that the proposed IB 2 OA outperforms the state-of-the-art methods in terms of precision, accuracy, recall, and F-score. In addition, when compared to the state-of-the-art, the proposed model's average selected features score is 4.425. In addition, among all classifiers considered, KNN classifier achieved the highest classification accuracy on the test dataset.

Abstract Photovoltaic (PV) system performance and reliability can be improved through the detection of defects in PV modules and the evaluation of their effects on system operation. In this paper, a novel system is proposed to detect and classify defects based on electroluminescence (EL) images. This system is called Fault Detection and Classification (FDC) and splits into four modules, which are (1) Image Preprocessing Module (IPM), (2) Feature Extraction Module (FEM), (3) Feature Selection Module (FSM), and (4) Classification Module (CM). In the first module (i.e., IPM), the EL images are preprocessed to enhance the quality of the images. Next, the two types of features in these images are extracted and fused together through FEM. Then, during FSM, the most important and informative features are extracted from these features using a new feature selection methodology, namely, Feature Selection-based Chaotic Map (FS-CM). FS-CM consists of two stages: filter stage using chi-square to initially select the most effective features and a modified selection stage using an enhanced version of Butterfly Optimization Algorithm (BOA). In fact, BOA is a popular swarm-based metaheuristic optimization algorithm that has only recently found success. While BOA has many benefits, it also has some drawbacks, including a smaller population and an increased likelihood of getting stuck in a local optimum. In this paper, a new methodology is proposed to improve the performance of BOA, called chaotic-based butterfly optimization algorithm. Finally, these selected features are used to feed the proposed classification model through CM. During CM, Hybrid Classification Model (HCM) is proposed. HCM consists of two stages, which are binary classification stage using Naïve Bayes (NB) and multi-class classification stage using enhanced multi-layer perceptron. According to the experimental results, the proposed system FDC outperforms the most recent methods. FDC introduced 98.2%, 89.23%, 87.2%, 87.9%, 87.55%, and 88.20% in terms of accuracy, precision, sensitivity, specificity, g-mean, and f-measure in the same order.

Abstract As the economy has grown rapidly in recent years, more and more people have begun putting their money into the stock market. Thus, predicting trends in the stock market is regarded as a crucial endeavor, and one that has proven to be more fruitful than others. Profitable investments will result in rising stock prices. Investors face significant difficulties making stock market-related predictions due to the lack of movement and noise in the data. In this paper, a new system for predicting stock market prices is introduced, namely stock market prediction based on deep leaning (SMP-DL). SMP-DL splits into two stages, which are (i) data preprocessing (DP) and (ii) stock price’s prediction (SP 2 ). In the first stage, data are preprocessed to obtain cleaned ones through several stages which are detect and reject missing value, feature selection, and data normalization. Then, in the second stage (e.g., SP 2 ), the cleaned data will pass through the used predicted model. In SP 2 , long short-term memory (LSTM) combined with bidirectional gated recurrent unit (BiGRU) to predict the closing price of stock market. The obtained results showed that the proposed system perform well when compared to other existing methods. As RMSE, MSE, MAE, and R 2 values are 0.2883, 0.0831, 0.2099, and 0.9948. Moreover, the proposed method was applied using different datasets and it performs well.

Abstract Breast cancer, which is also the leading cause of death among women, is one of the most common forms of the disease that affects females all over the world. The discovery of breast cancer at an early stage is extremely important because it allows selecting appropriate treatment protocol and thus, stops the development of cancer cells. In this paper, a new patients detection strategy has been presented to identify patients with the disease earlier. The proposed strategy composes of two parts which are data preprocessing phase and patient detection phase (PDP). The purpose of this study is to introduce a feature selection methodology for determining the most efficient and significant features for identifying breast cancer patients. This method is known as new hybrid feature selection method (NHFSM). NHFSM is made up of two modules which are quick selection module that uses information gain, and feature selection module that uses hybrid bat algorithm and particle swarm optimization. Consequently, NHFSM is a hybrid method that combines the advantages of bat algorithm and particle swarm optimization based on filter method to eliminate many drawbacks such as being stuck in a local optimal solution and having unbalanced exploitation. The preprocessed data are then used during PDP in order to enable a quick and accurate detection of patients. Based on experimental results, the proposed NHFSM improves the efficiency of patients’ classification in comparison with state-of-the-art feature selection approaches by roughly 0.97, 0.76, 0.75, and 0.716 in terms of accuracy, precision, sensitivity/recall, and F-measure. In contrast, it has the lowest error rate value of 0.03.